Navigation mark detection based on deep learning models from UAV images

Abstract

Prosperous waterway economics require rigorous safety measures. Unmanned aerial vehicle (UAV) offers massive images of inland waterways, within which navigation mark detection plays a critical role in ensuring waterway safety. This paper proposes a deep learning-based method for detecting navigation marks in UAV images. Firstly, a dataset of inland waterway navigation marks is constructed from UAV aerial images, which includes data collection, image enhancement, sample creation, and sample annotation. Secondly, a deep learning network model is developed, which uses ResNet-50 as the backbone, incorporates Coordinate Attention and Large-Scale Selective Kernel Attention mechanisms, integrates a Feature Pyramid Network (FPN) for feature enhancement, and uses Distance Intersection over Union (DIoU) as the loss function. Thirdly, the model is trained and evaluated on the constructed dataset, followed by precision assessment and post-processing. This paper explore a deep learning network model for small object detection in UAV images and establish a comprehensive workflow for detecting inland waterway navigation marks, thereby providing technical support for waterway safety.

Keywords

Deep learning / Small object detection / Faster R-CNN / UAV Image / Navigation mark detection / Navigation mark dataset

References

[1] Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S. End-to-end object detection with transformers. In Proceedings of the European Conference on Computer Vision, 2020, 2020: 213-229.

[2] Chen Y, Lin H, Xiao L, Zhang M, Zhang P. A novel method for water surface debris detection based on Yolov8 with polarization interference suppression. In Proceedings of the Photonics, 2025, 2025: 620.

[3] Cheng G, Yuan X, Yao X, Yan K, Zeng Q, Xie X, Han J. Towards large-scale small object detection: Survey and benchmarks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45: 13467-13488.

[4] Dong C, Loy CC, He K, Tang X. Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 38: 295-307.

[5] Everingham M, Van Gool L, Williams CK, Winn J, Zisserman A. The pascal visual object classes (Voc) challenge. International Journal of Computer Vision, 2010, 88: 303-338.

[6] Fefilatyev S, Goldgof D, Shreve M, Lembke C. Detection and tracking of ships in open sea with rapidly moving buoy-mounted camera system. Ocean Engineering, 2012, 54: 1-12.

[7] Ge, H. (2022). Research on intelligent recognition technology of navigation aid appearance status based on deep learning. Dalian Maritime University, 2022. https://doi.org/10.26989/d.cnki.gdlhu.2022.001110

[8] Hammedi, W., Ramirez-Martinez, M., Brunet, P., Senouci, S.-M., Messous, M.A. (2019). Deep learning-based real-time. 1–6. https://doi.org/10.1109/GLOBECOM38437.2019.9013931 object detection in inland navigation. In Proceedings of the 2019 IEEE global communications conference (GLOBECOM), 2019; pp

[9] Li C, Zhao R, Wang Z, Xu H, Zhu X. Remdet: Rethinking efficient model design for Uav object detection. In Proceedings of the Proceedings of the AAAI Conference on Artificial Intelligence, 2025, 2025: 4643-4651.

[10] Li, Z. (2022). Research on panoramic perception technology of ship navigation environment based on multi-camera. Dalian Maritime University, 2022. https://doi.org/10.26989/d.cnki.gdlhu.2022.001127

[11] Liu, C., Tao, Y., Liang, J., Li, K., Chen, Y. (2018). Object detection based on Yolo network. In Proceedings of the 2018 IEEE 4th information technology and mechatronics engineering conference (ITOEC), 2018, 799–803. https://doi.org/10.1109/ITOEC.2018.8740604

[12] Lu, Y., Guo, J., Guo, S., Fu, Q., Xu, J. (2022). Study on marine fishery law enforcement inspection system based on improved Yolo V5 with Uav. In Proceedings of the 2022 IEEE International Conference on Mechatronics and Automation (ICMA), 2022, 253–258. https://doi.org/10.1109/ICMA54519.2022.9856327

[13] Luo X, Wu Y, Chen J. Research progress on deep learning methods for object detection and semantic segmentation in Uav aerial images. Acta Aeronautica Et Astronautica Sinica, 2024, 45: 235-264

[14] McMillan, C., Zhao, J., Xue, B., Vennell, R., Zhang, M. (2023). Improving buoy detection with deep transfer learning for mussel farm automation. In Proceedings of the 2023 38^th International Conference on Image and Vision Computing New Zealand (IVCNZ), 2023, 1–6. https://doi.org/10.1109/IVCNZ61134.2023.10343657

[15] Moosbauer, S., König, D., Jäkel, J., Teutsch, M. (2019). A benchmark for deep learning based object detection in maritime environments. In Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 916–925. https://doi.org/10.1109/CVPRW.2019.00121

[16] Ni H, Chu X, Jiang Z. Inland navigation mark detection algorithm based on improved cascade Rcnn. Navigation of China, 2022, 45: 99-105

[17] Ni, H. (2021). Research on association rules and image recognition algorithm for inland waterway navigation accident. Wuhan University Technology, 2021. https://doi.org/10.27381/d.cnki.gwlgu.2021.001226

[18] Nikouei M, Baroutian B, Nabavi S, Taraghi F, Aghaei A, Sajedi A, Moghaddam ME. Small object detection: A comprehensive survey on challenges, techniques and real-world applications. Intelligent Systems with Applications, 2025arXiv preprint arXiv:2503.20516 2025

[19] Pan M, Liu Y, Cao J, Li Y, Li C, Chen C-H. Visual recognition based on deep learning for navigation mark classification. IEEE Access, 2020, 8: 32767-32775.

[20] Pan, H., Wu, X., Liu, X., Wang, T. (2021). High-quality development strategy for inland water transportation in China in the new era. Port & Waterway Engineering, 10, 14–19. https://doi.org/10.16233/j.cnki.issn1002-4972.20210924.054

[21] Peng L, Zhang Y, Ma S. Maritime small object detection algorithm in drone aerial images based on improved Yolov8. IEEE Access, 2024, 12: 176527-176538.

[22] Qu J, Liu R, Guo Y, Lu Y, Su J, Li P. Improving maritime traffic surveillance in inland waterways using the robust fusion of AIS and visual data. Ocean Engineering, 2023, 275: 114198.

[23] Quan Z, Sun J. A feature-enhanced small object detection algorithm based on attention mechanism. Sensors, 2025, 25: 589.

[24] Shao Z, Wu W, Wang Z, Du W, Li C. Seaships: A large-scale precisely annotated dataset for ship detection. IEEE Transactions on Multimedia, 2018, 20: 2593-2604.

[25] Song L, Deng H, Han J, Gao X. Improved aerial surface floating object detection and classification recognition algorithm based on Yolov8n. Sensors (Basel), 2025, 25: 1938.

[26] van Leeuwen MC, Fokkinga EP, Huizinga W, Baan J, Heslinga FG. Toward versatile small object detection with temporal-Yolov8. Sensors (Basel), 2024, 24: 7387.

[27] Wang N, Wang Y, Wei Y, Han B, Feng Y. Marine vessel detection dataset and benchmark for unmanned surface vehicles. Applied Ocean Research, 2024, 142: 103835.

[28] Wang Y, Zhang J, Zhou J. Urban traffic tiny object detection via attention and multi-scale feature driven in Uav-vision. Scientific Reports, 2024, 14: 20614.

[29] Wang K, He G, Li X. A lightweight multi-scale context detail network for efficient target detection in resource-constrained environments. Sensors (Basel), 2025, 25: 3800.

[30] Wang, P., Zhao, J. (2025). Sod-Yolo: enhancing Yolo-based detection of small objects in Uav imagery. arXiv preprint arXiv:2507.12727, 2025. https://doi.org/10.48550/arXiv.2507.12727

[31] Wu K, Chen Y, Lu Y, Yang Z, Yuan J, Zheng E. Sod-yolo: A high-precision detection of small targets on high-voltage transmission lines. Electronics, 2024, 13: 1371.

[32] Wu, P. (2010). Opportunity and challenge of inland navigation development in China. Port & Waterway Engineering, 2, 11–16. https://doi.org/10.16233/j.cnki.issn1002-4972.2010.02.033

[33] Zhan W, Sun C, Wang M, She J, Zhang Y, Zhang Z, Sun Y. An improved Yolov5 real-time detection method for small objects captured by UAV. Soft Computing, 2022, 26: 361-373.

[34] Zhang P, Liu Y. A small target detection algorithm based on improved Yolov5 in aerial image. PeerJ Computer Science, 2024, 10: e2007.

[35] Zhang C, Yue J, Fu J, Wu S. River floating object detection with transformer model in real time. Scientific Reports, 2025, 15: 9026.

[36] Zhang, L., Zhang, Y., Zhang, Z., Shen, J., Wang, H. (2019). Real-time water surface object detection based on improved faster R-Cnn. Sensors, 19, 17. https://doi.org/10.3390/s19163523

[37] Zhang, Z., Wagn, S., Tian, T. (2023). Inland waterway navigation aid telemetry monitoring system based on wireless sensor network. China Water Transport, 11, 58–60. https://doi.org/10.13646/j.cnki.42-1395/u.2023.06.021

[38] Zhu X, Zhang J, Zeng L, Liu B. Design of an intelligent monitoring system for inland waterway navigation marks based on Beidou. China Water Transport, 2022, 9: 56-58

RIGHTS & PERMISSIONS

The Author(s)